PiperOrigin-RevId: 157360504

Author: Googler

CONTRIBUTING.md

@@ -0,0 +1,30 @@
+Want to contribute? Great! First, read this page (including the small print at the end).
+
+### Before you contribute
+
+Before we can use your code, you must sign the
+[Google Individual Contributor License Agreement]
+(https://cla.developers.google.com/about/google-individual)
+(CLA), which you can do online. The CLA is necessary mainly because you own the
+copyright to your changes, even after your contribution becomes part of our
+codebase, so we need your permission to use and distribute your code. We also
+need to be sure of various other things—for instance that you'll tell us if you
+know that your code infringes on other people's patents. You don't have to sign
+the CLA until after you've submitted your code for review and a member has
+approved it, but you must do it before we can put your code into our codebase.
+Before you start working on a larger contribution, you should get in touch with
+us first through the issue tracker with your idea so that we can help out and
+possibly guide you. Coordinating up front makes it much easier to avoid
+frustration later on.
+
+### Code reviews
+
+All submissions, including submissions by project members, require review. We
+use Github pull requests for this purpose.
+
+### The small print
+
+Contributions made by corporations are covered by a different agreement than
+the one above, the
+[Software Grant and Corporate Contributor License Agreement]
+(https://cla.developers.google.com/about/google-corporate).

LICENSE

@@ -0,0 +1,202 @@
+
+                                 Apache License
+                           Version 2.0, January 2004
+                        http://www.apache.org/licenses/
+
+   TERMS AND CONDITIONS FOR USE, REPRODUCTION, AND DISTRIBUTION
+
+   1. Definitions.
+
+      "License" shall mean the terms and conditions for use, reproduction,
+      and distribution as defined by Sections 1 through 9 of this document.
+
+      "Licensor" shall mean the copyright owner or entity authorized by
+      the copyright owner that is granting the License.
+
+      "Legal Entity" shall mean the union of the acting entity and all
+      other entities that control, are controlled by, or are under common
+      control with that entity. For the purposes of this definition,
+      "control" means (i) the power, direct or indirect, to cause the
+      direction or management of such entity, whether by contract or
+      otherwise, or (ii) ownership of fifty percent (50%) or more of the
+      outstanding shares, or (iii) beneficial ownership of such entity.
+
+      "You" (or "Your") shall mean an individual or Legal Entity
+      exercising permissions granted by this License.
+
+      "Source" form shall mean the preferred form for making modifications,
+      including but not limited to software source code, documentation
+      source, and configuration files.
+
+      "Object" form shall mean any form resulting from mechanical
+      transformation or translation of a Source form, including but
+      not limited to compiled object code, generated documentation,
+      and conversions to other media types.
+
+      "Work" shall mean the work of authorship, whether in Source or
+      Object form, made available under the License, as indicated by a
+      copyright notice that is included in or attached to the work
+      (an example is provided in the Appendix below).
+
+      "Derivative Works" shall mean any work, whether in Source or Object
+      form, that is based on (or derived from) the Work and for which the
+      editorial revisions, annotations, elaborations, or other modifications
+      represent, as a whole, an original work of authorship. For the purposes
+      of this License, Derivative Works shall not include works that remain
+      separable from, or merely link (or bind by name) to the interfaces of,
+      the Work and Derivative Works thereof.
+
+      "Contribution" shall mean any work of authorship, including
+      the original version of the Work and any modifications or additions
+      to that Work or Derivative Works thereof, that is intentionally
+      submitted to Licensor for inclusion in the Work by the copyright owner
+      or by an individual or Legal Entity authorized to submit on behalf of
+      the copyright owner. For the purposes of this definition, "submitted"
+      means any form of electronic, verbal, or written communication sent
+      to the Licensor or its representatives, including but not limited to
+      communication on electronic mailing lists, source code control systems,
+      and issue tracking systems that are managed by, or on behalf of, the
+      Licensor for the purpose of discussing and improving the Work, but
+      excluding communication that is conspicuously marked or otherwise
+      designated in writing by the copyright owner as "Not a Contribution."
+
+      "Contributor" shall mean Licensor and any individual or Legal Entity
+      on behalf of whom a Contribution has been received by Licensor and
+      subsequently incorporated within the Work.
+
+   2. Grant of Copyright License. Subject to the terms and conditions of
+      this License, each Contributor hereby grants to You a perpetual,
+      worldwide, non-exclusive, no-charge, royalty-free, irrevocable
+      copyright license to reproduce, prepare Derivative Works of,
+      publicly display, publicly perform, sublicense, and distribute the
+      Work and such Derivative Works in Source or Object form.
+
+   3. Grant of Patent License. Subject to the terms and conditions of
+      this License, each Contributor hereby grants to You a perpetual,
+      worldwide, non-exclusive, no-charge, royalty-free, irrevocable
+      (except as stated in this section) patent license to make, have made,
+      use, offer to sell, sell, import, and otherwise transfer the Work,
+      where such license applies only to those patent claims licensable
+      by such Contributor that are necessarily infringed by their
+      Contribution(s) alone or by combination of their Contribution(s)
+      with the Work to which such Contribution(s) was submitted. If You
+      institute patent litigation against any entity (including a
+      cross-claim or counterclaim in a lawsuit) alleging that the Work
+      or a Contribution incorporated within the Work constitutes direct
+      or contributory patent infringement, then any patent licenses
+      granted to You under this License for that Work shall terminate
+      as of the date such litigation is filed.
+
+   4. Redistribution. You may reproduce and distribute copies of the
+      Work or Derivative Works thereof in any medium, with or without
+      modifications, and in Source or Object form, provided that You
+      meet the following conditions:
+
+      (a) You must give any other recipients of the Work or
+          Derivative Works a copy of this License; and
+
+      (b) You must cause any modified files to carry prominent notices
+          stating that You changed the files; and
+
+      (c) You must retain, in the Source form of any Derivative Works
+          that You distribute, all copyright, patent, trademark, and
+          attribution notices from the Source form of the Work,
+          excluding those notices that do not pertain to any part of
+          the Derivative Works; and
+
+      (d) If the Work includes a "NOTICE" text file as part of its
+          distribution, then any Derivative Works that You distribute must
+          include a readable copy of the attribution notices contained
+          within such NOTICE file, excluding those notices that do not
+          pertain to any part of the Derivative Works, in at least one
+          of the following places: within a NOTICE text file distributed
+          as part of the Derivative Works; within the Source form or
+          documentation, if provided along with the Derivative Works; or,
+          within a display generated by the Derivative Works, if and
+          wherever such third-party notices normally appear. The contents
+          of the NOTICE file are for informational purposes only and
+          do not modify the License. You may add Your own attribution
+          notices within Derivative Works that You distribute, alongside
+          or as an addendum to the NOTICE text from the Work, provided
+          that such additional attribution notices cannot be construed
+          as modifying the License.
+
+      You may add Your own copyright statement to Your modifications and
+      may provide additional or different license terms and conditions
+      for use, reproduction, or distribution of Your modifications, or
+      for any such Derivative Works as a whole, provided Your use,
+      reproduction, and distribution of the Work otherwise complies with
+      the conditions stated in this License.
+
+   5. Submission of Contributions. Unless You explicitly state otherwise,
+      any Contribution intentionally submitted for inclusion in the Work
+      by You to the Licensor shall be under the terms and conditions of
+      this License, without any additional terms or conditions.
+      Notwithstanding the above, nothing herein shall supersede or modify
+      the terms of any separate license agreement you may have executed
+      with Licensor regarding such Contributions.
+
+   6. Trademarks. This License does not grant permission to use the trade
+      names, trademarks, service marks, or product names of the Licensor,
+      except as required for reasonable and customary use in describing the
+      origin of the Work and reproducing the content of the NOTICE file.
+
+   7. Disclaimer of Warranty. Unless required by applicable law or
+      agreed to in writing, Licensor provides the Work (and each
+      Contributor provides its Contributions) on an "AS IS" BASIS,
+      WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or
+      implied, including, without limitation, any warranties or conditions
+      of TITLE, NON-INFRINGEMENT, MERCHANTABILITY, or FITNESS FOR A
+      PARTICULAR PURPOSE. You are solely responsible for determining the
+      appropriateness of using or redistributing the Work and assume any
+      risks associated with Your exercise of permissions under this License.
+
+   8. Limitation of Liability. In no event and under no legal theory,
+      whether in tort (including negligence), contract, or otherwise,
+      unless required by applicable law (such as deliberate and grossly
+      negligent acts) or agreed to in writing, shall any Contributor be
+      liable to You for damages, including any direct, indirect, special,
+      incidental, or consequential damages of any character arising as a
+      result of this License or out of the use or inability to use the
+      Work (including but not limited to damages for loss of goodwill,
+      work stoppage, computer failure or malfunction, or any and all
+      other commercial damages or losses), even if such Contributor
+      has been advised of the possibility of such damages.
+
+   9. Accepting Warranty or Additional Liability. While redistributing
+      the Work or Derivative Works thereof, You may choose to offer,
+      and charge a fee for, acceptance of support, warranty, indemnity,
+      or other liability obligations and/or rights consistent with this
+      License. However, in accepting such obligations, You may act only
+      on Your own behalf and on Your sole responsibility, not on behalf
+      of any other Contributor, and only if You agree to indemnify,
+      defend, and hold each Contributor harmless for any liability
+      incurred by, or claims asserted against, such Contributor by reason
+      of your accepting any such warranty or additional liability.
+
+   END OF TERMS AND CONDITIONS
+
+   APPENDIX: How to apply the Apache License to your work.
+
+      To apply the Apache License to your work, attach the following
+      boilerplate notice, with the fields enclosed by brackets "[]"
+      replaced with your own identifying information. (Don't include
+      the brackets!)  The text should be enclosed in the appropriate
+      comment syntax for the file format. We also recommend that a
+      file or class name and description of purpose be included on the
+      same "printed page" as the copyright notice for easier
+      identification within third-party archives.
+
+   Copyright [yyyy] [name of copyright owner]
+
+   Licensed under the Apache License, Version 2.0 (the "License");
+   you may not use this file except in compliance with the License.
+   You may obtain a copy of the License at
+
+       http://www.apache.org/licenses/LICENSE-2.0
+
+   Unless required by applicable law or agreed to in writing, software
+   distributed under the License is distributed on an "AS IS" BASIS,
+   WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+   See the License for the specific language governing permissions and
+   limitations under the License.

README.md

@@ -0,0 +1,3 @@
+# TensorFlow NMT Tutorial
+
+This is not an official Google product.

nmt/.gitignore

@@ -0,0 +1,4 @@
+bazel-bin
+bazel-genfiles
+bazel-out
+bazel-testlogs

nmt/__init__.py

@@ -0,0 +1,131 @@
+"""Attention-based sequence-to-sequence model with dynamic RNN support."""
+from __future__ import absolute_import
+from __future__ import division
+from __future__ import print_function
+
+import tensorflow as tf
+
+import model
+import model_helper
+
+__all__ = ["AttentionModel"]
+
+
+class AttentionModel(model.Model):
+  """Sequence-to-sequence dynamic model with attention.
+
+  This class implements a multi-layer recurrent neural network as encoder,
+  and an attention-based decoder. This is the same as the model described in
+  (Luong et al., EMNLP'2015) paper: https://arxiv.org/pdf/1508.04025v5.pdf.
+  This class also allows to use GRU cells in addition to LSTM cells with
+  support for dropout.
+  """
+
+  def __init__(self, hparams, mode, iterator,
+               source_vocab_table, target_vocab_table, scope=None):
+    super(AttentionModel, self).__init__(
+        hparams=hparams,
+        mode=mode,
+        iterator=iterator,
+        source_vocab_table=source_vocab_table,
+        target_vocab_table=target_vocab_table,
+        scope=scope)
+    if self.mode == tf.contrib.learn.ModeKeys.INFER:
+      self.infer_summary = (
+          _create_attention_images_summary(self.final_context_state,
+                                           hparams.alignment_history))
+
+  def _build_decoder_cell(self, hparams, encoder_outputs, encoder_state,
+                          source_sequence_length):
+    """Build a RNN cell with attention mechanism that can be used by decoder."""
+    attention_option = hparams.attention
+    attention_architecture = hparams.attention_architecture
+
+    if attention_architecture != "top":
+      raise ValueError(
+          "Unknown attention architecture %s" % attention_architecture)
+
+    num_units = hparams.num_units
+    num_layers = hparams.num_layers
+    num_residual_layers = hparams.num_residual_layers
+    num_gpus = hparams.num_gpus
+
+    dtype = tf.float32
+
+    attention_mechanism = create_attention_mechanism(
+        attention_option, num_units, encoder_outputs, self.time_major,
+        source_sequence_length)
+
+    cell = model_helper.create_rnn_cell(
+        hparams, num_layers, num_residual_layers, self.mode)
+
+    cell = tf.contrib.seq2seq.AttentionWrapper(
+        cell,
+        attention_mechanism,
+        attention_layer_size=num_units,
+        alignment_history=hparams.alignment_history,
+        name="attention")
+
+    #  do we need num_layers, num_gpus?
+    cell = tf.contrib.rnn.DeviceWrapper(
+        cell, model_helper.get_device_str(num_layers - 1, num_gpus))
+
+    batch_size = self.get_batch_size(encoder_outputs)
+    decoder_initial_state = cell.zero_state(batch_size, dtype).clone(
+        cell_state=encoder_state)
+
+    return cell, decoder_initial_state
+
+
+def create_attention_mechanism(attention_option, num_units, encoder_outputs,
+                               time_major, source_sequence_length):
+  """Create attention mechanism based on the attention_option."""
+  if time_major:
+    attention_states = tf.transpose(encoder_outputs, [1, 0, 2])
+  else:
+    attention_states = encoder_outputs
+
+  # Mechanism
+  if attention_option == "luong":
+    attention_mechanism = tf.contrib.seq2seq.LuongAttention(
+        num_units,
+        attention_states,
+        memory_sequence_length=source_sequence_length)
+  elif attention_option == "scaled_luong":
+    attention_mechanism = tf.contrib.seq2seq.LuongAttention(
+        num_units,
+        attention_states,
+        memory_sequence_length=source_sequence_length,
+        scale=True)
+  elif attention_option == "bahdanau":
+    attention_mechanism = tf.contrib.seq2seq.BahdanauAttention(
+        num_units,
+        attention_states,
+        memory_sequence_length=source_sequence_length)
+  elif attention_option == "normed_bahdanau":
+    attention_mechanism = tf.contrib.seq2seq.BahdanauAttention(
+        num_units,
+        attention_states,
+        memory_sequence_length=source_sequence_length,
+        normalize=True)
+  else:
+    raise ValueError("Unknown attention option %s" % attention_option)
+
+  return attention_mechanism
+
+
+def _create_attention_images_summary(final_context_state, alignment_history):
+  """create attention image and attention summary."""
+  if alignment_history:
+    attention_images = (
+        final_context_state.alignment_history.stack())
+  else:
+    attention_images = tf.zeros([1, 1, 1])
+
+  # Reshape to (batch, src_seq_len, tgt_seq_len,1)
+  attention_images = tf.expand_dims(
+      tf.transpose(attention_images, [1, 2, 0]), -1)
+  # Scale to range [0, 255]
+  attention_images *= 255
+  attention_summary = tf.summary.image("attention_images", attention_images)
+  return attention_summary